Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4064 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2456. Min Range: -1.2456

Max Act: 1.2182. Min Act: 0.0000

Data Index: 1607801 (The Pile)

Max Activating Token Index: 274

Text #1

Max Range: 1.2456. Min Range: -1.2456

Max Act: 1.1575. Min Act: -0.0000

Data Index: 1506605 (The Pile)

Max Activating Token Index: 63

Text #2

Max Range: 1.2456. Min Range: -1.2456

Max Act: 1.2456. Min Act: -0.0000

Data Index: 1468384 (The Pile)

Max Activating Token Index: 788

Text #3

Max Range: 1.2456. Min Range: -1.2456

Max Act: 1.0900. Min Act: -0.0000

Data Index: 736579 (The Pile)

Max Activating Token Index: 568

Text #4

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.8910. Min Act: -0.0000

Data Index: 119491 (The Pile)

Max Activating Token Index: 522

Text #5

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.8792. Min Act: -0.0000

Data Index: 727484 (The Pile)

Max Activating Token Index: 478

Text #6

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.9031. Min Act: -0.0000

Data Index: 845505 (The Pile)

Max Activating Token Index: 287

Text #7

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1941134 (The Pile)

Max Activating Token Index: 473

Text #8

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1680173 (The Pile)

Max Activating Token Index: 873

Text #9

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1503194 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.8077. Min Act: -0.0000

Data Index: 834801 (The Pile)

Max Activating Token Index: 332

Text #11

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.7806. Min Act: -0.0000

Data Index: 149982 (The Pile)

Max Activating Token Index: 340

Text #12

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1595060 (The Pile)

Max Activating Token Index: 752

Text #13

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1097442 (The Pile)

Max Activating Token Index: 278

Text #14

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.7694. Min Act: -0.0000

Data Index: 156705 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.8883. Min Act: -0.0000

Data Index: 839327 (The Pile)

Max Activating Token Index: 80

Text #16

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1770803 (The Pile)

Max Activating Token Index: 387

Text #17

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1452363 (The Pile)

Max Activating Token Index: 1019

Text #18

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.7477. Min Act: -0.0000

Data Index: 929383 (The Pile)

Max Activating Token Index: 589

Text #19

Max Range: 1.2456. Min Range: -1.2456

Max Act: 0.8463. Min Act: -0.0000

Data Index: 805529 (The Pile)

Max Activating Token Index: 244